Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.5625. Min Act: -0.1700
Data Index: 1308570 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.2813. Min Act: -0.1700
Data Index: 5297213 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.2813. Min Act: -0.1700
Data Index: 2403573 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7996650 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7380822 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.1250. Min Act: -0.1700
Data Index: 5713175 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.1250. Min Act: -0.1700
Data Index: 1127149 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7735818 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.1250. Min Act: -0.1700
Data Index: 1037491 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0938. Min Act: -0.1700
Data Index: 8686986 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0625. Min Act: -0.1700
Data Index: 3273033 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7130379 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7933771 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0938. Min Act: -0.1700
Data Index: 1057838 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0625. Min Act: -0.1700
Data Index: 7848556 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0625. Min Act: -0.1700
Data Index: 5053139 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0625. Min Act: -0.1700
Data Index: 7378055 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4976965 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0313. Min Act: -0.1700
Data Index: 2090448 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5625. Min Range: -6.5625
Max Act: 6.0313. Min Act: -0.1700
Data Index: 3498782 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19